ReLeaf: Benchmarking Leaf Segmentation across Domains and Species

• URL: http://arxiv.org/abs/2605.03784v1
• Date: Tue, 05 May 2026 14:11:52 GMT
• Title: ReLeaf: Benchmarking Leaf Segmentation across Domains and Species
• Abstract summary: Leaf-level segmentation is used to assess crop health, growth dynamics, yield potential and localized stress symptoms.<n>Progress is limited by a lack of dedicated datasets, especially regarding species coverage.<n>We introduce a new benchmark dataset with leaf-level masks for 23 plant species, created via semi-automatic annotation of selected CropAndWeed images.<n>A model trained on all four existing datasets achieves a mean mAP50-95 of 83.9% across their corresponding test sets and 40.2% on our new benchmark.
• Score: 2.446672595462589
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Rising global food demand and growing climate pressure increase the need for sustainable, precise agricultural practices. Automated, individualized plant treatment relies on fine-grained visual analysis, yet leaf-level segmentation remains underexplored despite its value for assessing crop health, growth dynamics, yield potential and localized stress symptoms. Progress is limited by a lack of dedicated datasets, especially regarding species coverage, and by the absence of systematic evaluations of modern instance-segmentation architectures for this task. We address these gaps by surveying current data and identifying four suitable, publicly available leaf-segmentation datasets. Using them, we compare one-stage, two-stage and Transformer-based detectors and identify a YOLO26 model configuration to provide the best trade-off for real-world precision-agriculture tasks. Extensive cross-domain generalization experiments reveal substantial performance drops across plant species and recording setups, especially for models trained solely on laboratory data. To strengthen data availability, we introduce a new benchmark dataset with leaf-level masks for 23 plant species, created via semi-automatic annotation of selected CropAndWeed images. A model trained on all four existing datasets achieves a mean mAP50-95 of 83.9% across their corresponding test sets and 40.2% on our new benchmark, demonstrating improved generalization and highlighting the need for diverse leaf-segmentation datasets in robust precision agriculture.

Related papers

• CropVLM: A Domain-Adapted Vision-Language Model for Open-Set Crop Analysis [0.0]
  We present CropVLM, a vision-language model adapted for the agricultural domain via Domain-Specific Semantic Alignment (DSSA)<n>CropVLM is trained on 52,987 manually selected image-caption pairs covering 37 species in natural field conditions.<n>In comprehensive evaluations, CropVLM achieves 72.51% zero-shot classification accuracy, outperforming seven CLIP-style baselines.
  arXiv  Detail & Related papers  (2026-05-05T01:17:27Z)
• It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks [87.7937890373758]
  Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.<n>We introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks.<n>We propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels.
  arXiv  Detail & Related papers  (2026-02-12T16:31:01Z)
• DepthCropSeg++: Scaling a Crop Segmentation Foundation Model With Depth-Labeled Data [8.868203469534269]
  DepthCropSeg++ is a foundation model for crop segmentation, capable of segmenting different crop species under open in-field environment.<n>We build upon a state-of-the-art semantic segmentation architecture ViT-Adapter architecture, enhance it with dynamic upAdapter architecture, and train the model with a two-stage selftraining pipeline.<n>Results demonstrate that DepthCropSeg++ achieves 93.11% moU on a comprehensive testing set, outperforming both supervised baselines and general vision foundation models.
  arXiv  Detail & Related papers  (2026-01-18T11:51:09Z)
• Vision Foundation Models in Agriculture: Toward Domain-Specific Adaptation for Weed Herbicide Trials Assessment [1.8430060563461854]
  Herbicide field trials require accurate identification of plant species and assessment of herbicide-induced damage.<n>In this work, we adapt a general-purpose vision foundation model to herbicide trial characterization.<n> Trained using a self-supervised learning approach on a large, curated agricultural dataset, the model learns rich and transferable representations optimized for herbicide trials images.
  arXiv  Detail & Related papers  (2025-11-06T11:30:32Z)
• Generating Diverse Agricultural Data for Vision-Based Farming Applications [74.79409721178489]
  This model is capable of simulating distinct growth stages of plants, diverse soil conditions, and randomized field arrangements under varying lighting conditions. Our dataset includes 12,000 images with semantic labels, offering a comprehensive resource for computer vision tasks in precision agriculture.
  arXiv  Detail & Related papers  (2024-03-27T08:42:47Z)
• Towards Biologically Plausible and Private Gene Expression Data Generation [47.72947816788821]
  Generative models trained with Differential Privacy (DP) are becoming increasingly prominent in the creation of synthetic data for downstream applications. Existing literature, however, primarily focuses on basic benchmarking datasets and tends to report promising results only for elementary metrics and relatively simple data distributions. We initiate a systematic analysis of how DP generative models perform in their natural application scenarios, specifically focusing on real-world gene expression data.
  arXiv  Detail & Related papers  (2024-02-07T14:39:11Z)
• GEO-Bench: Toward Foundation Models for Earth Monitoring [139.77907168809085]
  We propose a benchmark comprised of six classification and six segmentation tasks. This benchmark will be a driver of progress across a variety of Earth monitoring tasks.
  arXiv  Detail & Related papers  (2023-06-06T16:16:05Z)
• CWD30: A Comprehensive and Holistic Dataset for Crop Weed Recognition in Precision Agriculture [1.64709990449384]
  We present the CWD30 dataset, a large-scale, diverse, holistic, and hierarchical dataset tailored for crop-weed recognition tasks in precision agriculture. CWD30 comprises over 219,770 high-resolution images of 20 weed species and 10 crop species, encompassing various growth stages, multiple viewing angles, and environmental conditions. The dataset's hierarchical taxonomy enables fine-grained classification and facilitates the development of more accurate, robust, and generalizable deep learning models.
  arXiv  Detail & Related papers  (2023-05-17T09:39:01Z)
• Domain Generalization for Crop Segmentation with Standardized Ensemble Knowledge Distillation [42.39035033967183]
  Service robots need a real-time perception system that understands their surroundings and identifies their targets in the wild. Existing methods, however, often fall short in generalizing to new crops and environmental conditions. We propose a novel approach to enhance domain generalization using knowledge distillation.
  arXiv  Detail & Related papers  (2023-04-03T14:28:29Z)
• Agave crop segmentation and maturity classification with deep learning data-centric strategies using very high-resolution satellite imagery [101.18253437732933]
  We present an Agave tequilana Weber azul crop segmentation and maturity classification using very high resolution satellite imagery. We solve real-world deep learning problems in the very specific context of agave crop segmentation. With the resulting accurate models, agave production forecasting can be made available for large regions.
  arXiv  Detail & Related papers  (2023-03-21T03:15:29Z)
• Two-View Fine-grained Classification of Plant Species [66.75915278733197]
  We propose a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained recognition of plant species. A deep metric based on Siamese convolutional neural networks is used to reduce the dependence on a large number of training samples and make the method scalable to new plant species.
  arXiv  Detail & Related papers  (2020-05-18T21:57:47Z)
• Scalable learning for bridging the species gap in image-based plant phenotyping [2.208242292882514]
  The traditional paradigm of applying deep learning -- collect, annotate and train on data -- is not applicable to image-based plant phenotyping. Data costs include growing physical samples, imaging and labelling them. Model performance is impacted by the species gap between the domain of each plant species.
  arXiv  Detail & Related papers  (2020-03-24T10:26:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.